English
Related papers

Related papers: The Typical Behavior of Bandit Algorithms

200 papers

We propose $\tt RandUCB$, a bandit strategy that builds on theoretically derived confidence intervals similar to upper confidence bound (UCB) algorithms, but akin to Thompson sampling (TS), it uses randomization to trade off exploration and…

Machine Learning · Computer Science 2020-03-24 Sharan Vaswani , Abbas Mehrabian , Audrey Durand , Branislav Kveton

The multi-armed bandit (MAB) problem is a classical learning task that exemplifies the exploration-exploitation tradeoff. However, standard formulations do not take into account {\em risk}. In online decision making systems, risk is a…

Machine Learning · Computer Science 2020-08-04 Qiuyu Zhu , Vincent Y. F. Tan

We study the distribution of regret in stochastic multi-armed bandits and episodic reinforcement learning through a unified framework. We formalize a distributional regret bound as a probabilistic guarantee that holds uniformly over all…

Machine Learning · Computer Science 2026-05-08 Harin Lee , Min-hwan Oh

Bayesian bandit algorithms with approximate Bayesian inference have been widely used in real-world applications. Despite the superior practical performance, their theoretical justification is less investigated in the literature, especially…

Machine Learning · Statistics 2025-05-23 Ziyi Huang , Henry Lam , Haofeng Zhang

UCT, a state-of-the art algorithm for Monte Carlo tree sampling (MCTS), is based on UCB, a sampling policy for the Multi-armed Bandit Problem (MAB) that minimizes the accumulated regret. However, MCTS differs from MAB in that only the final…

Artificial Intelligence · Computer Science 2012-07-26 David Tolpin , Solomon Eyal Shimony

We consider a continuous-time multi-arm bandit problem (CTMAB), where the learner can sample arms any number of times in a given interval and obtain a random reward from each sample, however, increasing the frequency of sampling incurs an…

Machine Learning · Computer Science 2023-04-20 Rahul Vaze , Manjesh K. Hanawal

We study the optimal trade-off between expectation and tail risk for regret distribution in the stochastic multi-armed bandit model. We fully characterize the interplay among three desired properties for policy design: worst-case…

Machine Learning · Statistics 2025-10-27 David Simchi-Levi , Zeyu Zheng , Feng Zhu

In this study, we propose a new method for constructing UCB-type algorithms for stochastic multi-armed bandits based on general convex optimization methods with an inexact oracle. We derive the regret bounds corresponding to the convergence…

Machine Learning · Computer Science 2024-02-13 Yuriy Dorn , Aleksandr Katrutsa , Ilgam Latypov , Andrey Pudovikov

This paper considers the use of a simple posterior sampling algorithm to balance between exploration and exploitation when learning to optimize actions such as in multi-armed bandit problems. The algorithm, also known as Thompson Sampling,…

Machine Learning · Computer Science 2014-02-04 Daniel Russo , Benjamin Van Roy

We consider a stochastic bandit problem with countably many arms that belong to a finite set of types, each characterized by a unique mean reward. In addition, there is a fixed distribution over types which sets the proportion of each type…

Machine Learning · Computer Science 2021-05-25 Anand Kalvit , Assaf Zeevi

We study the regret of Thompson sampling (TS) algorithms for exponential family bandits, where the reward distribution is from a one-dimensional exponential family, which covers many common reward distributions including Bernoulli,…

Machine Learning · Statistics 2022-06-09 Tianyuan Jin , Pan Xu , Xiaokui Xiao , Anima Anandkumar

We consider a stochastic multi-armed bandit setting and study the problem of constrained regret minimization over a given time horizon. Each arm is associated with an unknown, possibly multi-dimensional distribution, and the merit of an arm…

Machine Learning · Computer Science 2023-01-05 Anmol Kagrecha , Jayakrishnan Nair , Krishna Jagannathan

Several optimism-based stochastic bandit algorithms -- including UCB, UCB-V, linear UCB, and finite-arm GP-UCB -- achieve logarithmic regret using proofs that, despite superficial differences, follow essentially the same structure. This…

Machine Learning · Computer Science 2025-12-23 Vikram Krishnamurthy

When multi-armed bandit (MAB) algorithms allocate pulls among competing arms, the resulting allocation can exhibit huge variation. This is particularly harmful in modern applications such as learning-enhanced platform operations and…

Machine Learning · Computer Science 2026-02-10 Yilun Chen , Jiaqi Lu

We study the problem of regret minimization in a multi-armed bandit setup where the agent is allowed to play multiple arms at each round by spreading the resources usually allocated to only one arm. At each iteration the agent selects a…

Machine Learning · Computer Science 2021-06-01 Matias I. Müller , Cristian R. Rojas

We consider regret minimization in a general collaborative multi-agent multi-armed bandit model, in which each agent faces a finite set of arms and may communicate with other agents through a central controller. The optimal arm for each…

Machine Learning · Computer Science 2023-12-18 Amitis Shidani , Sattar Vakili

We consider a contextual combinatorial bandit problem where in each round a learning agent selects a subset of arms and receives feedback on the selected arms according to their scores. The score of an arm is an unknown function of the…

Machine Learning · Statistics 2023-06-02 Taehyun Hwang , Kyuwook Chai , Min-hwan Oh

We study a stochastic bandit algorithm motivated by retry-aware objectives that value the best outcome among multiple attempts, such as pass@$k$ and max@$k$. Given a posterior over arm values, ReMax chooses a sampling distribution that…

Machine Learning · Computer Science 2026-05-21 Bingkui Tong , Junpei Komiyama , Soichiro Nishimori , Paavo Parmas

Motivated by the challenges of edge inference, we study a variant of the cascade bandit model in which each arm corresponds to an inference model with an associated accuracy and error probability. We analyse four decision-making…

Machine Learning · Computer Science 2026-03-30 R Sri Prakash , Nikhil Karamchandani , Sharayu Moharir

Multi-armed bandit problems are considered as a paradigm of the trade-off between exploring the environment to find profitable actions and exploiting what is already known. In the stationary case, the distributions of the rewards do not…

Statistics Theory · Mathematics 2008-12-18 Aurélien Garivier , Eric Moulines